Predicting Playa Inundation Using a Long Short-Term Memory Neural Network
This work addresses the need to model playa inundation for ecological and groundwater management, but it is incremental as it applies an existing LSTM method to a new domain-specific dataset.
The researchers tackled the problem of predicting inundation in playas, which are critical wetlands in the Great Plains, by using an LSTM neural network to model complex hydrological processes from 1984 to 2018, achieving an F1-score of 0.538 at the individual playa level and closely tracking regional inundation trends.
In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally-important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short-term memory (LSTM) neural network to account for these complex processes, we modeled playa inundation for 71,842 playas in the Great Plains from 1984-2018. At the level of individual playas, the model achieved an F1-score of 0.538 on a withheld test set, displaying the ability to predict complex inundation patterns. When averaging over all the playas in the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate.